Like how crypto used ASICS but then didn't because the scaling of consumer hardware made it obsolete?

To the extent that cryptocurrency moved off ASICs, it was because of interest shifting to different cryptocurrencies that were specifically designed to be harder to mine on an ASIC than Bitcoin's compute-heavy, memory-light hashing.

I'm not sure there's any reason to expect a similar shift from LLMs. The hardware used for training doesn't dictate what hardware needs to be used for inference, and nobody's going to design an LLM architecture with an overt intention to make it better suited to GPUs and hard to target with ASICs.

▲

SPascareli13 a day ago | parent [-]

Yet it doesn't seem that ASICs will have any particular advantage over consumer hardware since AI is very memory heavy, which is (right now) expensive no matter how you package it. And the compute is just simple matrix multiplication, which is almost entirely what GPUs were meant to do anyway.

▲

wtallis a day ago | parent | next [-]

ASIC vs GPU doesn't make a ton of difference when both are relying on commodity DRAM; in that sense, LLMs are more like the anti-ASIC cryptocurrencies. But the actually interesting ASICs are the ones that ditch the commodity discrete DRAM chips. They lose out on the memory density and thus struggle to scale up to the largest models, but for what does fit onto a Cerebras wafer or a Taalas chip, the speed is phenomenal. They have a real shot at securing the "smart enough, and really fast" segment of the market.

And it seems more plausible to me that an ASIC architecture rather than GPUs would be able to best make use of something like wafer-bonded custom memory to approach the density of discrete DRAM while retaining the extremely high bandwidth that comes with arbitrarily wide interfaces and minimal PHYs.

▲

infecto a day ago | parent | prev | next [-]

Go back and correct your idea that consumer hardware made asics obsolete. Then we can figure out if asic or asic like devices for inference will have no advantage.

▲

andy_ppp a day ago | parent | prev | next [-]

Except Taalas is much faster than GPUs, orders of magnitude so. They aren’t going to get 100x faster at inference any time soon!

	▲	SPascareli13 5 hours ago \| parent [-]
		There's a new SOTA model every few months, are you supposed to buy a new chip every new release?

▲

mitxela a day ago | parent | prev [-]

Yeah! Nobody needs chatjimmy.ai. Nobody needs their results to come back instantly instead of at 10 tokens per second. Nobody needs a CPU faster than a megahertz.

▲

infecto a day ago | parent | prev | next [-]

This is factually wrong no? Bitcoin is asic only. The others all changed for other reasons unrelated to your thought.

	▲	SPascareli13 5 hours ago \| parent [-]
		My thought was that ASICs turned out not to be worth it for crypto mining because consumer hardware evolved fast enough to do it, while also being cheaper and having some resale value, while ASICs are useless besides mining and have no resale value. So I'm extrapolating this same idea to LLM inference.

▲

connicpu a day ago | parent | prev | next [-]

x86 has a built in instruction for doing AES. That's just moving the ASIC into the CPU core, not eliminating it.

▲

gpugreg 21 hours ago | parent [-]

Is there any cryptocurrency that uses AES?

	▲	connicpu 10 hours ago \| parent [-]
		I hate the word crypto, very ambiguous. In my professional life it almost always refers to cryptography.

▲

actionfromafar a day ago | parent | prev [-]

Am I missing some joke here?